Protzko

@protzko.bsky.social

Experimental Psychologist, social perceptions, metascience. I study the assumptions you make. Here just trying to share good research https://sites.google.com/view/assumptionlabccsu/home

Dispositional properties, epistemics vs. metaphysics, even the hint of formative indicators. This piece is as succinct as it gets on why Polygenic Risk scores shouldn't be treated as objective indicators of outcome probability.

Eric Turkheimer@ent3c.bsky.social · 3mo ago

With @remyfurrer.bsky.social, a new piece in Nature Human Behavior. The standard description of a polygenic score as a "genetic predisposition" essentializes a statistical construct. It's not language policing: PGS are a new kind of entity; now is the time to think carefully about what they are.

I'm frequently amazed at the assumption that you can understand what a course is simply by eyeballing the syllabus. 3 professors with the exact same syllabus & reading list could teach 3 wildly different courses, even opposed to one another. Do we scrape syllabi because that's where the light is?

The OLS estimator is not the same as Pearl's do-calculus. ASSUME X2 confounds the relationship between X1 and Y. How sure are we that + X2 in a linear regression equation using the OLS estimator is actually doing the same thing as 'closing the back-door path' in a DAG? #stats

Message to all researchers (not calling anyone out) We'll start believing you want people to stop chasing journal Impact Factors As soon as You stop dropping the name of the journal your new article is in when you promote it on social media. Double fault if you only do it when IF is high #phdsky

Looking for a #SAS user who is interested in computational reproducibility to join a many-analysts-style paper. Run some #stats in SAS, get authorship, contribute to the world of reproducibility. If this is you or you know someone DM or email me (protzko@gmail) #phdsky

I feel like "The conclusions of this paper are fully in line with the corresponding author's whole schtick so they really want them to be true" should count as a conflict of interest #phdsky

for undergrads getting their degrees this Fall: if u're computationally savvy & wants to get into cog neuro -- instead of taking up lab manager / RA positions, why not come to Korea & get a master's degree instead? it will be all paid for w/ stipend, of coz. why would u pay for a master's degree??

Out in PNAS pnas.org/doi/10.1073/... Inequality is not only hard to solve. Sometimes, it is hard to *see*. We ask a simple question: Do people notice when members of minority groups are absent? Across field studies and experiments, the answer was often no.

PNAS

Proceedings of the National Academy of Sciences (PNAS), a peer reviewed journal of the National Academy of Sciences (NAS) - an authoritative source of high-impact, original research that broadly spans...

pnas.org

Version of this problem for online recipes: 5⭐️ - I didn't make it but it Looks wonderful! 4⭐️ - I made it but messed something up, my fault, tastes good enough though. 3 ⭐️ -?? 2 ⭐️ -??? 1 ⭐️ - I messed something up and it's your fault I replaced carrots with kale in your carrot cake recipe.

Skoo Bly User@gapineesq.bsky.social · last mo.

It’s a real problem that so many rating systems nowadays reduce to something like 5⭐️ - acceptable 4⭐️ - mediocre, serious problems 3 ⭐️ - I thought I would die 2 ⭐️ - the doctors said I should be dead 1 ⭐️ - my estate has filed a lawsuit There’s just no way to distinguish even outstanding/fine/poor

My 2 big, long-standing issues with multiverse analyses have been and continue to be: 1) they treat each analysis as valid (known to be false) 2) they treat each analysis as equally valid (also known to be false)

Daniel Lakens@lakens.bsky.social · 2mo ago

New preprint: There is only one correct analysis. osf.io/preprints/ps... with @sajedehra.bsky.social and @mntunc.bsky.social We take a critical look at recent proposals for multiverse or many analyst procedures, and strongly argue that epistemic uncertainty should be reduced, not “embraced”. >